Default to img_size in model default_cfg, defer output folder creation until later in the init sequence

* ModelEma class added to track an EMA set of weights for the model being trained
* EMA handling added to train, validation and clean_checkpoint scripts
* Add multi checkpoint or multi-model validation support to validate.py
* Add syncbn option (APEX) to train script for experimentation
* Cleanup interface of CheckpointSaver while adding ema functionality

* B0-B3 weights ported from TF with close to paper accuracy
* Renamed gen_mobilenet to gen_efficientnet since scaling params go well beyond 'mobile' specific
* Add Tensorflow preprocessing option for closer images to source repo

Add EfficientNet impl, change existing depth_multipler -> channel_multiplier as definitions have been confused

Fix bug for prefetcher

Set input and target to Cuda when without using prefetcher.

Update header comment

* Do mixup in custom collate fn if prefetcher enabled, reduces performance impact
* Move mixup code to own file
* Add arg to disable prefetcher
* Fix no cuda transfer when prefetcher off
* Random erasing when prefetcher off wasn't changed to match new args, fixed
* Default random erasing to off (prob = 0.) for train

* factor out data related constants to own file
* move data related config helpers to own file
* add a variant of RandomResizeCrop that randomizes interpolation method
* remove old Numpy version of RandomErasing
* cleanup torch version of RandomErasing and use it in either GPU loader batch mode or single image cpu Transform

* init square_avg with one instead of zero as per TF
* match TF order of ops for square_avg accumulation
* move LR scaling to momentum buffer accumulator as per TF
* add decoupled weight decay flag (not in TF)

Identity is not the same thing as equality in Python

Identity is not the same thing as equality in Python.  In these instances, we want the latter.

Use ==/!= to compare str, bytes, and int literals.

$ __python__
```python
>>> proj = "pro"
>>> proj += 'j'
>>> proj
'proj'
>>> proj == 'proj'
True
>>> proj is 'proj'
False
>>> 0 == 0.0
True
>>> 0 is 0.0
False
```
[flake8](http://flake8.pycqa.org) testing of https://github.com/rwightman/pytorch-image-models on Python 3.7.1

$ __flake8 . --count --select=E9,F63,F72,F82 --show-source --statistics__
```
./data/loader.py:48:23: F823 local variable 'input' defined as a builtin referenced before assignment
                yield input, target
                      ^
./models/dpn.py:170:12: F632 use ==/!= to compare str, bytes, and int literals
        if block_type is 'proj':
           ^
./models/dpn.py:173:14: F632 use ==/!= to compare str, bytes, and int literals
        elif block_type is 'down':
             ^
./models/dpn.py:177:20: F632 use ==/!= to compare str, bytes, and int literals
            assert block_type is 'normal'
                   ^
3     F632 use ==/!= to compare str, bytes, and int literals
1     F823 local variable 'input' defined as a builtin referenced before assignment
4
```
__E901,E999,F821,F822,F823__ are the "_showstopper_" [flake8](http://flake8.pycqa.org) issues that can halt the runtime with a SyntaxError, NameError, etc. These 5 are different from most other flake8 issues which are merely "style violations" -- useful for readability but they do not effect runtime safety.
* F821: undefined name `name`
* F822: undefined name `name` in `__all__`
* F823: local variable name referenced before assignment
* E901: SyntaxError or IndentationError
* E999: SyntaxError -- failed to compile a file into an Abstract Syntax Tree

* initial impl w/ label smoothing converging, but needs more testing

* fix expansion ratio on early block
* change comment re stride mistake in paper
* fix rounding not being called properly for all multipliers != 1.0

Add notes for latest mobile model weights...

Add support for tflite mnasnet pretrained weights and included spnasnet pretrained weights of my own.
* tensorflow 'SAME' padding support added to GenMobileNet models for tflite pretrained weights
* folded batch norm support (made batch norm optional and enable conv bias) for tflite pretrained weights
* add url for spnasnet1_00 weights that I recently trained
* fix SE reduction size for semnasnet models